{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XASBOPQEHRUD4V7YUKQTKECFMN","short_pith_number":"pith:XASBOPQE","canonical_record":{"source":{"id":"1911.09659","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T18:39:01Z","cross_cats_sorted":[],"title_canon_sha256":"104e719f68ddae8c3db1cf3a270bf59db22e063981d55dea2e924d1474b093b9","abstract_canon_sha256":"af8c52f586c22553d3d03ab3bf9ae90377b41d6d8aa77b8f307dd8aeda542685"},"schema_version":"1.0"},"canonical_sha256":"b824173e043c683e57f8a2a1351045634cfeb46cc567963c05d7fe3e1c06001c","source":{"kind":"arxiv","id":"1911.09659","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.09659","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"1911.09659v2","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09659","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"XASBOPQEHRUD","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"XASBOPQEHRUD4V7Y","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"XASBOPQE","created_at":"2026-07-05T00:24:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XASBOPQEHRUD4V7YUKQTKECFMN","target":"record","payload":{"canonical_record":{"source":{"id":"1911.09659","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T18:39:01Z","cross_cats_sorted":[],"title_canon_sha256":"104e719f68ddae8c3db1cf3a270bf59db22e063981d55dea2e924d1474b093b9","abstract_canon_sha256":"af8c52f586c22553d3d03ab3bf9ae90377b41d6d8aa77b8f307dd8aeda542685"},"schema_version":"1.0"},"canonical_sha256":"b824173e043c683e57f8a2a1351045634cfeb46cc567963c05d7fe3e1c06001c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:42.766034Z","signature_b64":"szJCgxUapyATdn8wvazbq5v9pAKtJqOpogjW8X9PcUGnglzMHEtxA1wc9VbiBwaEOwDrnhLKVGfAVrQNrDFDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b824173e043c683e57f8a2a1351045634cfeb46cc567963c05d7fe3e1c06001c","last_reissued_at":"2026-07-05T00:24:42.765532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:42.765532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.09659","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:24:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIhCxLd9TpYA6hbYQ2txbRUTSdy3A8vrqV7VGp0nOrJe/JFnd59FnqJsHJ9/KfgC2a1Gy0cZRMvI2h/QOXoEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T08:13:06.453137Z"},"content_sha256":"d94646395909fefd2d5b97903023a70bde1a4fd1f185595590a6fab3f0cf97c6","schema_version":"1.0","event_id":"sha256:d94646395909fefd2d5b97903023a70bde1a4fd1f185595590a6fab3f0cf97c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XASBOPQEHRUD4V7YUKQTKECFMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Wang, Tajana Rosing, Yandong Li, Yunhui Guo","submitted_at":"2019-11-21T18:39:01Z","abstract_excerpt":"There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper, we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09659","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.09659/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:24:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FwoFA9xXFzQ4WhP6z2YeDhjKznVvWDzNowTt6QgXVXPqjV3njXhwsQjI2/yYG4I7YnzuniL5DYeTs753RR7eDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T08:13:06.453526Z"},"content_sha256":"bec3d43f8deb1507de4d52765ef8058c6386cb1fecbf9a54d9a65f2639aff707","schema_version":"1.0","event_id":"sha256:bec3d43f8deb1507de4d52765ef8058c6386cb1fecbf9a54d9a65f2639aff707"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XASBOPQEHRUD4V7YUKQTKECFMN/bundle.json","state_url":"https://pith.science/pith/XASBOPQEHRUD4V7YUKQTKECFMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XASBOPQEHRUD4V7YUKQTKECFMN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T08:13:06Z","links":{"resolver":"https://pith.science/pith/XASBOPQEHRUD4V7YUKQTKECFMN","bundle":"https://pith.science/pith/XASBOPQEHRUD4V7YUKQTKECFMN/bundle.json","state":"https://pith.science/pith/XASBOPQEHRUD4V7YUKQTKECFMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XASBOPQEHRUD4V7YUKQTKECFMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XASBOPQEHRUD4V7YUKQTKECFMN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af8c52f586c22553d3d03ab3bf9ae90377b41d6d8aa77b8f307dd8aeda542685","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T18:39:01Z","title_canon_sha256":"104e719f68ddae8c3db1cf3a270bf59db22e063981d55dea2e924d1474b093b9"},"schema_version":"1.0","source":{"id":"1911.09659","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.09659","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"1911.09659v2","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09659","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"XASBOPQEHRUD","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"XASBOPQEHRUD4V7Y","created_at":"2026-07-05T00:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"XASBOPQE","created_at":"2026-07-05T00:24:42Z"}],"graph_snapshots":[{"event_id":"sha256:bec3d43f8deb1507de4d52765ef8058c6386cb1fecbf9a54d9a65f2639aff707","target":"graph","created_at":"2026-07-05T00:24:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.09659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper, we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-t","authors_text":"Liqiang Wang, Tajana Rosing, Yandong Li, Yunhui Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T18:39:01Z","title":"AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09659","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d94646395909fefd2d5b97903023a70bde1a4fd1f185595590a6fab3f0cf97c6","target":"record","created_at":"2026-07-05T00:24:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af8c52f586c22553d3d03ab3bf9ae90377b41d6d8aa77b8f307dd8aeda542685","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T18:39:01Z","title_canon_sha256":"104e719f68ddae8c3db1cf3a270bf59db22e063981d55dea2e924d1474b093b9"},"schema_version":"1.0","source":{"id":"1911.09659","kind":"arxiv","version":2}},"canonical_sha256":"b824173e043c683e57f8a2a1351045634cfeb46cc567963c05d7fe3e1c06001c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b824173e043c683e57f8a2a1351045634cfeb46cc567963c05d7fe3e1c06001c","first_computed_at":"2026-07-05T00:24:42.765532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:42.765532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"szJCgxUapyATdn8wvazbq5v9pAKtJqOpogjW8X9PcUGnglzMHEtxA1wc9VbiBwaEOwDrnhLKVGfAVrQNrDFDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:42.766034Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.09659","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d94646395909fefd2d5b97903023a70bde1a4fd1f185595590a6fab3f0cf97c6","sha256:bec3d43f8deb1507de4d52765ef8058c6386cb1fecbf9a54d9a65f2639aff707"],"state_sha256":"68382a60a11eda499a244788b48848fad0cfabec9688b8b9b8b8f56ab2de11d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8z/mdRDd0T4RmGCJhmQjbINblrRgvKkhXri1pA2M9bmKU/MZQXctHvScSva8ULZNpR9x6GpixdWYsYQmbJJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T08:13:06.455594Z","bundle_sha256":"c45de41df8d877c3486ae399ca6a82a80b09e998b7242ea8e3e98237e625b634"}}